Medical and Biological Engineering and Computing

, Volume 41, Issue 1, pp 101–106 | Cite as

Eye feature extraction for diagnosing the facial phenotype associated with fetal alcohol syndrome

  • T. S. Douglas
  • F. Martinez
  • E. M. Meintjes
  • C. L. Vaughan
  • D. L. Viljoen
Article
Received:
Accepted:

Abstract

Victims of fetal alcohol syndrome (FAS) exhibit a unique facial phenotype that is emphasised in diagnosis. Among the characteristic facial features, several occurring in the region of the orbits can be evaluated quantitatively using distance measurements. An algorithm is described for automatic extraction and measurement of eye features from stereo photographs. The algorithm was applied to photographs of 46 six-seven-year-old children. The approach relies on peak and valley maps and integral projection functions, to locate the eyes and extract the iris, and genetic algorithms to fit cubic splines to the upper and lower eyelids. Measurements obtained automatically using this algorithm were compared with measurements obtained manually from the photographs. Mean absolute differences between automatic and manual measurements were less than 1 mm for palpebral fissure length (PFL) and interpupillary distance (IPD). Absolute differences were less than 1 mm for 80.4% of PFLs and 100% of IPDs. Inner canthal distance and outer canthal distance did not compare favourably with manual measurements.

Keywords

Fetal alcohol syndrome Photogrammetry Facial Anthropometry Genetic algorithm Image processing 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abdel-Aziz, Y. I., andKarara, H. M. (1971): ‘Direct linear transformation from comparator coordinates into object space co-ordinates’. American Society of Photogrammetry Symposium on Close-Range Photogrammetry, Falls Church, Virginia, USA, pp. 1–18Google Scholar
  2. Astley, S. J., andClarren, S. K. (1996): ‘A case definition and photographic screening tool for the facial phenotype of fetal alcohol syndrome’,J. Pediatr.,129, pp. 33–41Google Scholar
  3. Astley, S. J., andClarren, S. K. (2001): ‘Measuring the facial phenotype of individuals with prenatal alcohol exposure: correlations with brain dysfunction’,Alcohol Alcoholism,36, pp. 147–159CrossRefGoogle Scholar
  4. Brunelli, R., andPoggio, T. (1993): ‘Face recognition: features versus templates,’IEEE Trans. Pattern Anal. Mach. Intell.,15, pp. 1042–1052CrossRefGoogle Scholar
  5. Croxford, J., andViljoen, D. (1999): ‘Alcohol consumption by pregnant women in the Western Cape’,South Afr. Med. J.,89, pp. 962–965Google Scholar
  6. Esme, B., Sankur, B., andAnarum, E. (1996): ‘Facial feature extraction using genetic algorithms’. Signal Processing VIII, Theories and Applidations, Proc. EUSIPCOGoogle Scholar
  7. Farkas, L. G. (1994): ‘Anthropometry of the head and face’ (Raven Press, NY, 1994), pp. 79–88Google Scholar
  8. Feng, G. C., andYuen, P. C. (1998): ‘Variance projection function and its application to eye detection for human face recognition’,Pattern Recognit. Lett.,19, pp. 899–906CrossRefGoogle Scholar
  9. Goldberg, D. E. (1989): ‘Genetic algorithms in search, optimization, and machine learning’ (Addison Wesley, New York, 1989)Google Scholar
  10. Hall, J. G., Froster-Iskenius, U. G., andAllanson, J. E. (1989): ‘Handbook of normal physiological measurements’ (Oxford University Press, Oxford, 1989)Google Scholar
  11. Iosub, S., Fuchs, M., Bingol, N., Stone, R. K., Gromisch, D. S., andWasserman, E. (1985): ‘Papebral fissure length in black and Hispanic children: correlation with head circumference’,Pediatrics,75, pp. 318–320Google Scholar
  12. Lam, K. M., andYan, H. (1996): ‘Locating and extracting the eye in human face images’,Pattern Recognit.,29, pp. 771–779Google Scholar
  13. May, P. A., Brooke, L., Gossage, J. P., Croxford, J., Adnams, C., Jones, K. L., Robinson, L., andViljoen, D. (2000): ‘Epidemiology of fetal alcohol syndrome in a South African community in the Western Cape province’,Am. J. Publ. Health,90, pp. 1905–1912Google Scholar
  14. Meintjes, E. M., Douglas, T. S., Martinez, F., Vaughan, C. L., Adams, L. P., Stekhoven, A., andViljoen, D. (2002): ‘A stereophotogrammetric method to measure the facial dysmorphology of children in the diagnosis of Fetal Alcohol Syndrome’,Med. Eng. Phys.,24, pp. 683–689CrossRefGoogle Scholar
  15. Ras, F., Habets, L. L. M. H., Van Ginkel, F. C., andPrahl-Andersen, B. (1996): ‘Quantification of facial morphology using stereophotogrammetry-demonstration of a new concept’,J. Dent.,24, pp. 369–374CrossRefGoogle Scholar
  16. Shaner, D. J., Bamforth, J. S., Petersen, A. E., andBeattie, O. B. (1998): ‘Technical note: different techniques, different results — A comparison of photogrammetric and caliper-derived measurements’,Am. J. Phys. Anthrop.,106, pp. 547–552CrossRefGoogle Scholar
  17. Smith, D. W. (1979): ‘The fetal alcohol syndrome’,Hosp. Pract., Oct., pp. 121–128Google Scholar
  18. Sobottka, K., andPitas, I. (1998): ‘A novel method for automatic face segmentation, facial feature extraction and tracking’,Signal Process. Image Commun.,12, pp. 263–281CrossRefGoogle Scholar
  19. Thomas, I. T., Gaitantzis, Y. A., andFrias, J. L. (1987): ‘Palpebral fissure length from 29 weeks gestation to 14 years’,J. Pediatr.,111, pp. 267–268Google Scholar
  20. Xie, X., Sudharkar, R., andZhuang, H. (1994): ‘On improving eye feature extraction using deformable templates’,Pattern Recognit.,27, pp. 791–799CrossRefGoogle Scholar
  21. Yuille, A. L., Hallinan, P. W., andCohen, D. S. (1992): ‘Feature extraction from faces using deformable templates’,Int. J. Comput. Vis.,8, pp. 99–111CrossRefGoogle Scholar

Copyright information

© IFMBE 2003

Authors and Affiliations

  • T. S. Douglas
    • 1
  • F. Martinez
    • 1
  • E. M. Meintjes
    • 1
  • C. L. Vaughan
    • 1
  • D. L. Viljoen
    • 2
  1. 1.MRC/UCT Medical Imaging Research Unit, Department of Human BiologyUniversity of Cape TownSouth Africa
  2. 2.Department of Human Genetics, South African Institute for Medical ResearchUniversity of the WitwatersrandSouth Africa

Personalised recommendations